{"list":"other","total":56,"rows":[{"id":"2103.00020","title":"Learning Transferable Visual Models From Natural Language Supervision","created":"2021-02-26","cited_by_count":33744},{"id":"2005.14165","title":"Language Models are Few-Shot Learners","created":"2020-05-28","cited_by_count":32419},{"id":"2112.10752","title":"High-Resolution Image Synthesis with Latent Diffusion Models","created":"2021-12-20","cited_by_count":18863},{"id":"2303.08774","title":"GPT-4 Technical Report","created":"2023-03-15","cited_by_count":18396},{"id":"1405.0312","title":"Microsoft COCO: Common Objects in Context","created":"2014-05-01","cited_by_count":17608},{"id":"2103.14030","title":"Swin Transformer: Hierarchical Vision Transformer using Shifted Windows","created":"2021-03-25","cited_by_count":12139},{"id":"2010.04159","title":"Deformable DETR: Deformable Transformers for End-to-End Object Detection","created":"2020-10-08","cited_by_count":3422},{"id":"2303.05499","title":"Grounding DINO: Marrying DINO with Grounded Pre-Training for Open-Set Object Detection","created":"2023-03-09","cited_by_count":3332},{"id":"1804.02767","title":"YOLOv3: An Incremental Improvement","created":"2018-04-08","cited_by_count":2659},{"id":"1912.04838","title":"Scalability in Perception for Autonomous Driving: Waymo Open Dataset","created":"2019-12-10","cited_by_count":2451},{"id":"1805.04687","title":"BDD100K: A Diverse Driving Dataset for Heterogeneous Multitask Learning","created":"2018-05-12","cited_by_count":1288},{"id":"1908.03195","title":"LVIS: A Dataset for Large Vocabulary Instance Segmentation","created":"2019-08-08","cited_by_count":1217},{"id":"1904.07850","title":"Objects as Points","created":"2019-04-16","cited_by_count":1175},{"id":"2112.03857","title":"Grounded Language-Image Pre-training","created":"2021-12-07","cited_by_count":1156},{"id":"2107.08430","title":"YOLOX: Exceeding YOLO Series in 2021","created":"2021-07-18","cited_by_count":1071},{"id":"1703.07402","title":"Simple Online and Realtime Tracking with a Deep Association Metric","created":"2017-03-21","cited_by_count":910},{"id":"2104.13921","title":"Open-vocabulary Object Detection via Vision and Language Knowledge Distillation","created":"2021-04-28","cited_by_count":906},{"id":"1602.00763","title":"Simple Online and Realtime Tracking","created":"2016-02-02","cited_by_count":868},{"id":"2110.06864","title":"ByteTrack: Multi-Object Tracking by Associating Every Detection Box","created":"2021-10-13","cited_by_count":823},{"id":"1609.01775","title":"Performance Measures and a Data Set for Multi-Target, Multi-Camera Tracking","created":"2016-09-06","cited_by_count":692},{"id":"2009.07736","title":"HOTA: A Higher Order Metric for Evaluating Multi-Object Tracking","created":"2020-09-16","cited_by_count":552},{"id":"1603.00831","title":"MOT16: A Benchmark for Multi-Object Tracking","created":"2016-03-02","cited_by_count":532},{"id":"2307.07635","title":"CoTracker: It is Better to Track Together","created":"2023-07-14","cited_by_count":522},{"id":"2101.02702","title":"TrackFormer: Multi-Object Tracking with Transformers","created":"2021-01-07","cited_by_count":518},{"id":"2004.01888","title":"FairMOT: On the Fairness of Detection and Re-Identification in Multiple Object Tracking","created":"2020-04-04","cited_by_count":490},{"id":"2004.01177","title":"Tracking Objects as Points","created":"2020-04-02","cited_by_count":483},{"id":"1809.07845","title":"LaSOT: A High-quality Benchmark for Large-scale Single Object Tracking","created":"2018-09-20","cited_by_count":429},{"id":"1903.05625","title":"Tracking without bells and whistles","created":"2019-03-13","cited_by_count":382},{"id":"2003.09003","title":"MOT20: A benchmark for multi object tracking in crowded scenes","created":"2020-03-19","cited_by_count":357},{"id":"2203.14360","title":"Observation-Centric SORT: Rethinking SORT for Robust Multi-Object Tracking","created":"2022-03-27","cited_by_count":346},{"id":"1803.10794","title":"TrackingNet: A Large-Scale Dataset and Benchmark for Object Tracking in the Wild","created":"2018-03-28","cited_by_count":343},{"id":"1909.12605","title":"Towards Real-Time Multi-Object Tracking","created":"2019-09-27","cited_by_count":311},{"id":"2306.08637","title":"TAPIR: Tracking Any Point with per-frame Initialization and temporal Refinement","created":"2023-06-14","cited_by_count":287},{"id":"2206.05836","title":"GLIPv2: Unifying Localization and Vision-Language Understanding","created":"2022-06-12","cited_by_count":275},{"id":"2211.03726","title":"TAP-Vid: A Benchmark for Tracking Any Point in a Video","created":"2022-11-07","cited_by_count":263},{"id":"2006.06664","title":"Quasi-Dense Similarity Learning for Multiple Object Tracking","created":"2020-06-11","cited_by_count":220},{"id":"2204.04153","title":"Particle Video Revisited: Tracking Through Occlusions Using Point Trajectories","created":"2022-04-08","cited_by_count":217},{"id":"2202.13514","title":"StrongSORT: Make DeepSORT Great Again","created":"2022-02-28","cited_by_count":213},{"id":"2306.05422","title":"Tracking Everything Everywhere All at Once","created":"2023-06-08","cited_by_count":193},{"id":"1409.7618","title":"Multiple Object Tracking: A Literature Review","created":"2014-09-26","cited_by_count":166},{"id":"2005.10356","title":"TAO: A Large-Scale Benchmark for Tracking Any Object","created":"2020-05-20","cited_by_count":147},{"id":"2010.07548","title":"MOTChallenge: A Benchmark for Single-Camera Multiple Target Tracking","created":"2020-10-15","cited_by_count":136},{"id":"1504.01942","title":"MOTChallenge 2015: Towards a Benchmark for Multi-Target Tracking","created":"2015-04-08","cited_by_count":133},{"id":"2302.11813","title":"Deep OC-SORT: Multi-Pedestrian Tracking by Adaptive Re-Identification","created":"2023-02-23","cited_by_count":132},{"id":"2006.09920","title":"Contrastive Learning for Weakly Supervised Phrase Grounding","created":"2020-06-17","cited_by_count":102},{"id":"2010.12138","title":"Rethinking the competition between detection and ReID in Multi-Object Tracking","created":"2020-10-23","cited_by_count":101},{"id":"2304.08408","title":"OVTrack: Open-Vocabulary Multiple Object Tracking","created":"2023-04-17","cited_by_count":53},{"id":"2104.11221","title":"Opening up Open-World Tracking","created":"2021-04-22","cited_by_count":50},{"id":"2207.12978","title":"Tracking Every Thing in the Wild","created":"2022-07-26","cited_by_count":44},{"id":"2103.15145","title":"TransCenter: Transformers with Dense Representations for Multiple-Object Tracking","created":"2021-03-28","cited_by_count":42},{"id":"2205.00158","title":"AnimalTrack: A Benchmark for Multi-Animal Tracking in the Wild","created":"2022-04-30","cited_by_count":37},{"id":"2207.05518","title":"Tracking Objects as Pixel-wise Distributions","created":"2022-07-12","cited_by_count":37},{"id":"2011.11858","title":"GMOT-40: A Benchmark for Generic Multiple Object Tracking","created":"2020-11-24","cited_by_count":32},{"id":"1911.02794","title":"A Survey on Edge Computing Systems and Tools","created":"2019-11-07","cited_by_count":17},{"id":"2101.08040","title":"1st Place Solution to ECCV-TAO-2020: Detect and Represent Any Object for Tracking","created":"2021-01-20","cited_by_count":17},{"id":"2308.11093","title":"Video OWL-ViT: Temporally-consistent open-world localization in video","created":"2023-08-22","cited_by_count":13}],"next_cursor":null}